Amplitude integration is here
Query your Amplitude product analytics (retention, funnels, user behavior, revenue) in natural language, right alongside your SQL data.
Contextflo now connects to Amplitude. Ask about retention, funnels, user behaviour and revenue in natural language, right alongside your SQL data. One conversation, both sources, instead of switching between Amplitude dashboards and your warehouse.

What you can ask
Once connected, you can query Amplitude the way you would ask a colleague:
What does our signup-to-purchase funnel look like this month?
What's our D1, D7 and D30 retention?
Which features do our most active users use?
Look up user [email protected] and show me their recent activity
Contextflo works out which Amplitude endpoints to call, passes the right parameters, and returns a clear answer.
The endpoints it covers
The integration wraps the Amplitude Dashboard REST API:
| Endpoint | What it gives you |
|---|---|
| Event Segmentation | Counts, uniques, DAU%, with grouping and filters |
| Funnel Analysis | Step-by-step conversion rates between events |
| Retention | D1/D7/D30 retention with pre-calculated percentages |
| Revenue LTV | ARPU, ARPPU, total revenue, paying users |
| User Search | Find users by email, user ID or Amplitude ID |
| User Activity | Full event stream for a specific user |
| User Composition | Breakdown by country, platform, device |
| User Counts | Active and new user trends over time |
| Event List | All tracked events with volume |
| Session Length | Distribution histogram of session durations |
| Avg Session Length | Average session duration over time |
| Sessions Per User | Average sessions per user over time |
| Real-time Active Users | Live count of currently active users |
| Chart Results | Pull data from saved Amplitude charts |
Event List is worth knowing about even though it sounds like plumbing. Amplitude event names are whatever someone typed when they instrumented the feature, so asking for the event list first is how you find out whether the thing you care about is called checkout_completed, purchase, or Purchase Completed before you build a funnel on the wrong one.
Cross-source answers
The real gain is combining Amplitude with your SQL data in one conversation.
What's the conversion rate from signup to purchase in Amplitude, and what's the average order value for converted users in our database?
Three things happen: the Amplitude funnel API is queried for signup → purchase conversion, your warehouse is queried for average order value, and the two are combined into one answer.
Before this, that meant opening Amplitude, building a funnel chart, exporting it, switching to a SQL tool, running a query, and reconciling the two by hand. The reconciling was always the annoying part, because Amplitude counts users and your database counts orders, and deciding which one is the denominator is a judgement call somebody had to make silently every time.
Getting started
Connect Amplitude in your Contextflo settings. You will need your Amplitude API Key and Secret Key, both under your Amplitude project settings. Once connected the endpoints are immediately available in your MCP client.
Works with Claude, Cursor, and any other MCP-compatible client.
Connect Amplitude and your warehouse and ask across both in Claude. Free for one user and one data source.